A new study published in Nature Communications introduces a foundation model designed to help clinicians assess patients with acute abdominal conditions using noncontrast computed tomography, or CT. Acute abdominal pain can arise from dozens of causes, ranging from self-limiting inflammation to internal bleeding, bowel obstruction, perforation or ischemia. A foundation model is intended to learn broad, reusable representations from large and varied datasets rather than being trained for only one narrowly defined diagnosis. A foundation model, by contrast, is designed as a general-purpose platform that can be adapted to multiple tasks. https://doi.org/10.1038/s41467-026-76634-wImage Credits: AI GeneratedDOI: 10.1038/s41467-026-76634-wKeywords: Foundation model, acute abdomen, noncontrast computed tomography, medical artificial intelligence, diagnosis stratification, clinical triage